Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9985. Min Act: -0.1700

Data Index: 6412314 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9785. Min Act: -0.1700

Data Index: 5678948 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9645. Min Act: -0.1700

Data Index: 304502 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9604. Min Act: -0.1700

Data Index: 1081913 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9435. Min Act: -0.1700

Data Index: 4280352 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 4869761 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 4021020 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 8769645 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 7194414 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 1681481 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 5814652 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9443. Min Act: -0.1700

Data Index: 1397991 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9264. Min Act: -0.1700

Data Index: 1404497 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9208. Min Act: -0.1700

Data Index: 8216097 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9153. Min Act: -0.1700

Data Index: 287857 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9224. Min Act: -0.1700

Data Index: 1443354 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9231. Min Act: -0.1700

Data Index: 5147706 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9176. Min Act: -0.1700

Data Index: 1535775 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9076. Min Act: -0.1700

Data Index: 2866745 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9033. Min Act: -0.1700

Data Index: 4115941 (Open Web Text)

Max Activating Token Index: 2